Machine learning protocol code

README.md

This project "A Machine Learning Protocol for Predicting Protein Infrared Spectra" was supported by Prof. Shaul Mukamel(the University of California, Irvine), Prof. Jonathan D. Hirst(University of Nottingham),and Prof.Jun Jiang(University of Science and Technology of China).

Simulation data and code of ML protocl for IR spectra of proteins.

Any researchers who interested in protein spectroscopy can use our ML protcol online service: http://dcaiku.com:12880/platform/first

For the machine learning protocol source code written in Python and Bash language which including:

1.1.py: Split the protein into individual peptide bonds and dipeptides.

1.2.py: Calculate the center of mass for each each peptide bond and dipeptide.

1.3.sh: Convert the pdb format file to xyz format

2.py: Extracte the Coulomb Matrix (CM) descriptors of peptide bond and dipeptide..

3.py: Predict the vibrational frequency and vibrational transition dipole moment of each peptide bond from trained NMA Neural Networks (NN) model.

4.py: Predict the neighboring coupling of each dipeptide from trained GLDP NN model.

5.sh: Generate the input file for SPECTRON program to calculate the IR spectra of proteins.

6.py: Construct the model Hamiltonian for amide I vibrations in a protein based on vibration exciton model theory.

IR.sh: Diagonalize the Hamilton matrix calculate the IR spectra by using the SPECTRON.